Eunki Kim
6 papers · 2025–2026 · 3 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+1 more ↓ Show less ↑
🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (22) ⭐ Rising Star (6) ⚡ Prolific Year · Productive
🌈
Renaissance Researcher
(5)
Top co-authors
Research topics
Machine Learning
(5)
Artificial Intelligence
(4)
Core AI
(4)
Deep Learning
(2)
Reinforcement Learning
(2)
Core Methods
(2)
Learning Types
(2)
Methods
(2)
Optimization & Theory
(2)
Computer Vision
(1)
Data Science & Analytics
(1)
Natural Language Processing
(1)
Application Areas
(1)
Architectures
(1)
Domain-Specific
(1)
Keywords
vision-language model
(2)
reinforcement learning
(1)
curriculum learning
(1)
preference learning
(1)
direct preference optimization
(1)
time series forecasting
(1)
bradley-terry model
(1)
modality gap
(1)
reward model
(1)
image-text retrieval
(1)
user feedback
(1)
normalization layer
(1)
contrastive language-image pretraining
(1)
preference data
(1)
air quality forecasting
(1)
zero-shot inference
(1)
group relative policy optimization
(1)
diagram description
(1)
latent supervision
(1)
large language model
(1)
Papers
Real-Time Long Horizon Air Quality Forecasting via Group-Relative Policy Optimization
CVPR 2026
AlphaPO: Reward Shape Matters for LLM Alignment
ICML 2025
I0T: Embedding Standardization Method Towards Zero Modality Gap
ACL 2025
Learning to Insert [PAUSE] Tokens for Better Reasoning
ACL 2025
On the Robustness of Reward Models for Language Model Alignment
ICML 2025
Sightation Counts: Leveraging Sighted User Feedback in Building a BLV-aligned Dataset of Diagram Descriptions
ACL 2025